In this paper, we explore the effect of self-training and co-training on Hindi dependency parsing using partial parses. We use Partial parser and apply self-training using a large unannotated corpus. For co-training, we use Malt and MST parser along with Partial Parser. We explore different criteria for choosing partial parses to be used for bootstrapping. Through these experiments, we compare the impact of self-training and co-training on Hindi dependency parsing.
展开▼
